频域注意力机制下的癫痫脑电信号分类

孙红帅; 王霞; 柳萱; 张连超; 赵兴杰

doi:10.7652/xjtuxb202102015

您当前的位置：

首页 >

文章列表页 >

频域注意力机制下的癫痫脑电信号分类

更新时间：2025-07-09

- 频域注意力机制下的癫痫脑电信号分类
- A Classification Method of Epileptic Electroencephalograms Under Frequency-Domain Attention Mechanism
- 西安交通大学学报 2021年55卷第2期页码：129-135
- 作者机构：
  
  西安交通大学电子与信息学部,西安,710049
- 作者简介：
- 基金信息：
  
  : 2020-06-15。作者简介: 孙红帅(1995—),男,硕士生;王霞(通信作者),女,教授。基金项目: 陕西省国际科技合作计划重点资助项目(2020KWZ-014)
- DOI：10.7652/xjtuxb202102015
  中图分类号： TN911.6
- 网络首发：2021-02-10，
  
  纸质出版：2021
- 稿件说明：
移动端阅览
孙红帅, 王霞, 柳萱, 等. 频域注意力机制下的癫痫脑电信号分类[J]. 西安交通大学学报, 2021,55(2):129-135.

A Classification Method of Epileptic Electroencephalograms Under Frequency-Domain Attention Mechanism[J]. 2021, 55(2): 129-135.
孙红帅, 王霞, 柳萱, 等. 频域注意力机制下的癫痫脑电信号分类[J]. 西安交通大学学报, 2021,55(2):129-135. DOI： 10.7652/xjtuxb202102015.

A Classification Method of Epileptic Electroencephalograms Under Frequency-Domain Attention Mechanism[J]. 2021, 55(2): 129-135. DOI： 10.7652/xjtuxb202102015.

摘要

为提高癫痫脑电信号特征分类的准确率

基于残差网络结构的深度学习

提出了一种频域注意力机制下的癫痫脑电信号分类(FDAM)算法。首先分析所提取的脑电信号特征

然后根据信号特征主要分布在时频域的幅值中的特点

通过残差网络对时频域幅值特征进行二次提取

最后为了使残差网络提取的特征集中在与分类结果相关性较大的频域

设计了一种频域注意力机制

在深度学习过程中增强该类频域的幅值特征

有效提高了癫痫脑电信号的分类准确率。采用公开数据库PhysioNet中的CHB-MIT Scalp EEG Database数据库对算法的分类性能进行了验证

实验结果表明

FDAM算法对正常状态和癫痫发作状态的脑电信号分类准确率达到98.05%

特异性为99.34%

灵敏度为96.12%。

Abstract

A classification method of epileptic EEG signals under frequency domain attention mechanism(FDAM)based on a deep learning of residual network structure is proposed to improve the classification accuracy of epileptic electroencephalogram(EEG)signals. Firstly

the algorithm of extracting epileptic EEG signal features is analyzed. Then

according to the characteristics of the amplitude that the signal features are mainly distributed in the time-frequency domain

the amplitude features in the time-frequency domain are extracted twice through the residual network. Finally

in order to focus the features extracted from the residual network on the frequency domain which is more relevant to the classification results

a frequency domain attention mechanism is designed to enhance the amplitude characteristics of the frequency domain in the process of deep learning and effectively improve the classification accuracy of epileptic EEG signals. The classification performance of the proposed algorithm is tested by experiments and the experimental data are obtained from the CHB-MIT Scalp EEG Database in the open PhysioNet database. The experimental results show that FDAM algorithm can classify EEG signals in normal state and epileptic state with 98.05% in accuracy

99.34% in specificity and 96.12% in sensitivity.

关键词

Keywords

references

SILBERMAN E K, WEINGARTIER H, 王益明. 情绪的大脑半球功能的单侧化 [J]. 心理科学进展, 1992(1): 26-31.

SILBERMAN E K, WEINGARTIER H, WANG Yiming. Unilateral hemispheric function of emotion [J]. Advances in Psychological Science, 1992(1): 26-31.

孟庆芳, 周卫东, 陈月辉, 等. 基于非线性预测效果的癫痫脑电信号的特征提取方法 [J]. 物理学报, 2010, 59(1): 123-130.

MENG Qingfang, ZHOU Weidong, CHEN Yuehui, et al. Feature extraction method of epileptic EEG signal based on nonlinear prediction effect [J]. Journal of Physics, 2010, 59(1): 123-130.

SAMIEE K, KOVACS P, GABBOUJ M. Epileptic seizure classification of EEG time-series using rational discrete short-time Fourier transform [J]. IEEE Trans-actions on Biomedical Engineering, 2015, 62(2): 541-552.

ALEXANDROS T, MARKOS G, DIMITRIOS I. Epileptic seizure detection in EEGs using time-frequency analysis [J]. IEEE Transactions on Information Technology in Biomedicine, 2009, 13(5): 703-710.

GHOSH-DASTIDAR S, ADELI H, DADMEHR N. Mixed-band wavelet-chaos-neural network methodo-ogy for epilepsy and epileptic seizure detection [J]. IEEE Transactions on Biomedical Engineering, 2007, 54(9): 1545-1551.

崔昊天, 宋森. 基于图注意力深度神经网络的癫痫脑电尖波识别 [J]. 生物学杂志, 2020(1): 11-15.

CUI Haotian, SONG Sen. Epileptic EEG sharp wave recognition based on graph attention depth neural network [J]. Journal of Biology, 2020(1): 11-15.

NIKNAZAR M, MOUSAVI S R, VAHDAT B V, et al. A new framework based on recurrence quantification analysis for epileptic seizure detection [J]. IEEE Journal of Biomedical and Health Informatics, 2013, 17(3): 572-578.

CHISCI L, MAVINO A, PERFERI G, et al. Real-time epileptic seizure prediction using AR models and support vector machines [J]. IEEE Transactions on Biomedical Engineering, 2010, 57(5): 1124-1132.

齐永锋, 李陇强. 基于局部模式的癫痫脑电信号自动分类方法 [J]. 计算机工程, 2020(2): 298-303.

QI Yongfeng, LI Longqiang. Automatic classification of epileptic EEG signals based on local mode [J]. Computer Engineering, 2020(2): 298-303.

CHAOCALITWONGSE W A, FAN Y J, SACHDEO R C. On the time series K-nearest neighbor classification of abnormal brain activity [J]. IEEE Transactions on Systems Man Cybernetics: Part A Systems Humans, 2007, 37(6): 1005-1016.

FAN Miaolin, CHOU Chun-An. Detecting abnormal pattern of epileptic seizures via temporal synchronization of EEG signals [J]. IEEE Transactions on Biomedical Engineering, 2019, 66(3): 601-608.

YUAN Ye, XUN Guangxu, JIA Kebin, et al. A multi-view deep learning framework for EEG seizure detection [J]. IEEE Journal of Biomedical Health Informatics, 2019, 23(1): 83-94.

MARCELO A C, MOHAMAD E S H J, JRAD N, et al. Time-varying time-frequency complexity measures for epileptic EEG data analysis [J]. IEEE Transactions on Biomedical Engineering, 2018, 65(8): 1681-1688.

WANG Dong, REN Doutian, LI Kuo, et al. Epileptic seizure detection in long-term EEG recordings by using wavelet-based directed transfer function [J]. IEEE Transactions on Biomedical Engineering, 2018, 65(11): 2591-2599.

ABHIJIT B, PACHORI R B. A multivariate approach for patient-specific EEG seizure detection using empirical wavelet transform [J]. IEEE Transactions on Biomedical Engineering, 2017, 64(9): 2003-2015.

ALDANA R Y, HUNYADI B, MARAMON R E J, et al. Nonconvulsive epileptic seizure detection in scalp EEG using multiway data analysis [J]. IEEE Journal of Biomedical and Health Informatics, 2019, 23(2): 660-671.

GU Zhenghui, YAN Gang, ZHANG Jun, et al. Automatic epilepsy detection based on wavelets constructed from data [J]. IEEE Access, 2018, 6: 53133-53140.

HE Kaiming, ZHANG Xiangyu, REN Shaoqing, et al. Deep residual learning for image recognition [C]∥29th IEEE Conference on Computer Vision Pattern Recognition. Los Alamitos, CA, USA: IEEE Computer Society, 2016: 770-778.

MUHAMMAD S J S, SAJID S, KHAWAR K, et al. Dynamic mode decomposition based epileptic seizure detection from scalp EG [J]. IEEE Access, 2018, 6: 38683-38692.

NHAN D T, LEVIN K, MOHAMMAD R B, et al. Epileptic seizure forecasting with generative adversarial networks [J]. IEEE Access, 2019, 7: 143999-144009.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

去除癫痫脑电信号运动伪迹的变分模态分解-自适应熵阈值方法

经验模态分解和Kolmogorov测度的癫痫预测算法

表情驱动下脑电信号的建模仿真及分类识别

结合运动想象和动作观察的伸-握动作识别方法

针对局灶性癫痫患者的脑电微状态分析